Security audit

fanqie-masterclass

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese web-fiction coaching skill with no hidden code or privileged system behavior, though its writing and monetization advice should be used carefully.

Install this only if you want Chinese-market web-fiction coaching. Review its aggressive trope, imitation, platform-publishing, payment, and tax suggestions against the rules of the services you use and applicable law; do not treat the W-8BEN or monetization sections as professional legal or tax advice.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (13)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description is broadly scoped around common user intents like learning, writing help, diagnosis, polishing, and monetization, which are phrases likely to appear in ordinary conversations. This can cause unintended invocation, leading the agent to activate the skill in contexts where the user did not explicitly request it, increasing the chance of irrelevant guidance or unexpected behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The quick-start section maps very common conversational phrases such as '怎么写', '帮我生成', '看看哪里不好', and '润色' directly to execution modes. Because these phrases are generic across many writing and editing tasks, the skill may trigger outside its intended niche, causing over-broad activation and potentially hijacking requests that should be handled by other skills or the base assistant.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The document is entirely framed as prescriptive Chinese writing guidance, including directives like '必须删除或替换' and '避免使用', but it does not indicate that this applies only when the user wants Chinese output. That can create a language/locale policy issue because it implicitly forces one language and style regime without opt-in or scope limitation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The document’s instructions and examples are fully presented in Chinese, and there is no natural-language indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file presents all instructional content in a single language and does not indicate that users can choose another language or locale. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The entire skill is written as prescriptive guidance in Chinese and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The entire document is written exclusively in Chinese and assumes Chinese-language platforms, workflows, and examples throughout, without offering any language or locale choice. Under the stated policy, forced language or locale constraints should be flagged unless they are explicitly documented and justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The embedded '万能翻译Prompt' hard-codes a target audience as '18-35岁的欧美女性读者（Native English speakers）' and directs the model to localize accordingly before any user preference is gathered. This can override user intent, constrain output to a specific locale/cultural framing, and produce unsuitable or biased content when the user did not request that audience targeting.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The title and throughout-content instructions are written as a prescriptive checklist for producing content in Chinese, with no indication that other languages are supported or optional. Under the policy rule, forcing a specific language or locale without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The entire skill content is written as prescriptive guidance in Chinese and does not indicate that the language is optional or limited to a region-specific use case. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file is written entirely in Chinese and presents prescriptive instructions and publication criteria such as '低于75分的标题禁止发布', with no indication that other languages are allowed. Under the language/locale policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructional content in a single language with no opt-in, alternative language option, or explanation that the skill is region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This markdown file provides all instructions, labels, and example prompts exclusively in Chinese, with no indication that users may choose another language or that the skill is limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy issue.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.